发表机构
The Hong Kong Polytechnic University; The Hong Kong Polytechnic University Shenzhen Research Institute; The Hong Kong Polytechnic University-Daya Bay Technology and Innovation Research Institute（香港理工大学; 香港理工大学深圳研究院; 香港理工大学-大亚湾技术与创新研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出多智能体框架EvoCoCo，通过语义引导重构多目标进化算法计算以实现自动张量化，在48个MOEAs基准测试中验证其迁移可靠性、优化保真度与GPU加速效果。
AI 中文摘要
多目标进化算法（MOEAs）天然具备种群级并行性，但许多成熟实现将其计算编码为针对中央处理器设计的顺序程序结构。因此，利用现代张量计算平台不仅需要直接的代码翻译，还必须在不改变底层MOEA核心优化机制的前提下重构实现。我们将MOEAs的自动张量化定义为语义引导的计算重构，并开发了Evolutionary Code Conversion（EvoCoCo）多智能体框架来实现该定义。EvoCoCo将算法特定的状态、依赖关系、算子和更新逻辑重构为结构化语义表示，并通过共享张量化蓝图对其进行组织。专门的转换分支会探索不同的张量实现，而执行反馈则指导验证、修复和候选选择。在包含48个MOEAs的基准测试上进行的实验评估了迁移可靠性、优化保真度和计算可扩展性。在匹配的大语言模型后端下，EvoCoCo比直接一次性翻译实现了更高的迁移可靠性。在整个基准测试套件中，88.2%的有效比较满足预定义的优化保真度准则。张量化实现还在图形处理单元上展现出随种群规模或决策维度增长而提升的加速效果，测量到的中位加速比范围为种群规模缩放下的22.6倍至决策维度缩放下的80.2倍。外部源研究和消融研究进一步评估了超出主基准的迁移能力以及主要框架组件的作用。
英文摘要
Multiobjective evolutionary algorithms (MOEAs) naturally expose population-level parallelism, but many mature implementations encode their computation in sequential program structures designed for central processing units. Exploiting modern tensor computing platforms therefore requires more than direct code translation: the implementation must be restructured without changing the defining optimization mechanism of the underlying MOEA. We formulate automatic tensorization for MOEAs as semantics-guided computational restructuring and develop Evolutionary Code Conversion (EvoCoCo), a multi-agent framework that realizes this formulation. EvoCoCo reconstructs algorithm-specific states, dependencies, operators, and update logic into a structured semantic representation and organizes them through a shared tensorization blueprint. Specialized transformation branches then explore alternative tensor realizations, while execution feedback guides validation, repair, and candidate selection. Experiments on a benchmark of 48 MOEAs evaluate migration reliability, optimization fidelity, and computational scalability. Under matched large language model backends, EvoCoCo attains higher migration reliability than direct one-shot translation. Across the benchmark suites, 88.2% of valid comparisons satisfy the predefined optimization-fidelity criterion. The tensorized implementations also exhibit increasing acceleration on graphics processing units as population size or decision dimension grows, with median measured speedups ranging from $22.6\times$ under population scaling to $80.2\times$ under decision-dimension scaling. External-source and ablation studies further assess transfer beyond the main benchmark and the roles of the major framework components.
